English
Related papers

Related papers: Statistical exponential families: A digest with fl…

200 papers

In this paper, we give a method to construct "good" exponential families systematically by representation theory. More precisely, we consider a homogeneous space $G/H$ as a sample space and construct an exponential family invariant under…

Statistics Theory · Mathematics 2022-10-14 Koichi Tojo , Taro Yoshino

Recently, G.~Yanev obtained a characterization of the exponential family of distributions in terms of a functional equation for certain mixture densities. The purpose of this note is twofold: we extend Yanev's theorem by relaxing a…

Probability · Mathematics 2022-03-22 Reza Rastegar , Alex Roitershtein

Minimization of suitable statistical distances~(between the data and model densities) has proved to be a very useful technique in the field of robust inference. Apart from the class of $\phi$-divergences of \cite{a} and \cite{b}, the…

Statistics Theory · Mathematics 2021-01-25 Sancharee Basak , Ayanendranath Basu

Exponential families are statistical models which are the workhorses in statistics, information theory, and machine learning among others. An exponential family can either be normalized subtractively by its cumulant or free energy function…

Information Theory · Computer Science 2024-02-27 Frank Nielsen

A set of independence statements may define the independence structure of interest in a family of joint probability distributions. This structure is often captured by a graph that consists of nodes representing the random variables and of…

Methodology · Statistics 2011-07-15 Nanny Wermuth

Exponential families and mixture families are parametric probability models that can be geometrically studied as smooth statistical manifolds with respect to any statistical divergence like the Kullback-Leibler (KL) divergence or the…

Machine Learning · Computer Science 2018-03-21 Frank Nielsen , Gaëtan Hadjeres

An expanded family of mixtures of multivariate power exponential distributions is introduced. While fitting heavy-tails and skewness has received much attention in the model-based clustering literature recently, we investigate the use of a…

Methodology · Statistics 2015-06-15 Utkarsh J. Dang , Ryan P. Browne , Paul D. McNicholas

We establish a one-to-one correspondence between the set of minimal exponential families of dimension n defined on a finite sample space {\Omega} and the affine Grassmannian associated to an appropriate vector space of functions.

Differential Geometry · Mathematics 2025-02-20 Danuzia Nascimento Figueirêdo , Hale Aytaç , Mathieu Molitor

We propose a novel approach for density estimation with exponential families for the case when the true density may not fall within the chosen family. Our approach augments the sufficient statistics with features designed to accumulate…

Machine Learning · Statistics 2012-09-07 Lin Yuan , Sergey Kirshner , Robert Givan

Starting from some considerations we make about the relations between certain difference statistics and the classical permutation statistics we study permutations whose inversion number and excedance difference coincide. It turns out that…

Combinatorics · Mathematics 2007-05-23 Astrid Reifegerste

In this paper, we introduce some particular families of graphicable algebras obtained by following a relatively new line of research, initiated previously by some of the authors. It consists of the use of certain objects of Discrete…

Rings and Algebras · Mathematics 2013-09-26 Juan Núñez , María Luisa Rodríguez-Arévalo , María Trinidad Villar

We give a complete classification of 1-dimensional exponential families $\mathcal{E}$ defined over a finite space $\Omega=\{x_{0}, ...,x_{n}\}$ whose Hessian scalar curvature is constant. We observe an interesting phenomenon: if…

Differential Geometry · Mathematics 2019-06-07 Mathieu Molitor

For the extended skew-normal distribution, which represents an extension of the normal (or Gaussian) distribution, we focus on the properties of the log-likelihood function and derived quantities in the the bivariate case. Specifically, we…

Statistics Theory · Mathematics 2023-09-20 Stefano Franco , Adelchi Azzalini

A sufficient statistic is a deterministic function that captures an essential property of a probabilistic function (channel, kernel). Being a sufficient statistic can be expressed nicely in terms of string diagrams, as Tobias Fritz showed…

Logic in Computer Science · Computer Science 2023-06-22 Bart Jacobs

Exponential varieties arise from exponential families in statistics. These real algebraic varieties have strong positivity and convexity properties, familiar from toric varieties and their moment maps. Among them are varieties of inverses…

Algebraic Geometry · Mathematics 2017-05-17 Mateusz Michałek , Bernd Sturmfels , Caroline Uhler , Piotr Zwiernik

In this paper we propose a Farlie-Gumbel-Morgenstern (FGM) family of bivariate linear exponential distributions generated from given marginal's. Therefore, properties of FGM are analogous to properties of bivariate distributions. We study…

Methodology · Statistics 2015-01-23 M. A. El-Damcese , Dina. A. Ramadan

Graphs derived from groups are a widely studied class of graphs, motivated by their highly symmetric structure. In particular, G-graphs offer an easy and interesting alternative construction of semi-symmetric graphs. After recalling the…

Combinatorics · Mathematics 2016-11-25 David Ellison , Ruxandra Marinescu-Ghemeci , Cerasela Tanasescu

Through viewing out the literature, many generated distributions took a new special form of probability density function (PDF) in which it is written as a linear combination of n other distributions. Therefore, we define in this paper a new…

Statistics Theory · Mathematics 2022-11-15 Therar Kadri , Amina Halat

We introduce a class of distributions originating from an exponential family and having a property related to the strict stability property. A characteristic function representation for this family is obtained and its properties are…

Methodology · Statistics 2010-06-11 Lev B. Klebanov , Grigory Temnov

Maximum likelihood learning with exponential families leads to moment-matching of the sufficient statistics, a classic result. This can be generalized to conditional exponential families and/or when there are hidden data. This document…

Machine Learning · Computer Science 2020-01-28 Justin Domke